ocr_text_vision

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and delivers useful context: on-device GPU/ANE inference, macOS 10.15+ requirement, and supported language coverage. It also transparently states the return format, though it does not discuss failure modes or supported image input formats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-structured, leading with the core purpose and output, then adding backend and platform trade-offs. Each sentence provides meaningful information without repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the essential purpose, output, backend, and platform fit, which is adequate for a simple OCR tool at a high level. However, it omits important context such as what lang and mode control, what image formats are accepted, and any failure behaviors, leaving clear gaps given the absence of output schema and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero description coverage, and the description itself gives no explanation of the meaning, allowed values, or acceptable formats for path, lang, or mode. The only parameter-related detail is the return format, which does not help an agent construct valid arguments.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific action, 'Extract text from an image', and clearly names the resource (images) plus the return payload (full text, per-line confidence, bounding boxes). It also distinguishes itself from sibling OCR tools by explicitly identifying the Apple Vision backend and the text vs. layout/table focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool: it is 'Best for CJK + major European languages' and 'Zero install on macOS', suggesting the intended environment. It does not explicitly name alternative tools like ocr_text_paddle or state when not to use this tool, so the guidelines lack exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.